Content-based Image Retrieval Using Haar Wavelet Transform and Color Moment

Abstract

Content-based image retrieval (CBIR) deals with the retrieval of most similar images corresponding to a query image from an image database by using visual contents of the image itself. It requires feature extraction and computation of similarity. In this paper, we propose a content-based image retrieval method that uses a combination of color and texture features. The Haar wavelet transform is used for texture feature extraction, and for color feature extraction we use color moments. The distance between the query image features and the database images’ features is computed by using Canberra distance. We assign weights to texture feature distance and color feature distance and calculate the similarity with combined feature distance. Experiment results reflect the importance of the Haar wavelet transform and color moments in the performance of our proposed CBIR method.